On a new anatomy QA benchmark, AlpaCare-13B beat Mistral-7B and BioMistral-7B-DARE in accuracy and safety, but all models dropped on complex reasoning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Truth, Trust, and Trouble: Medical AI on the Edge
On a new anatomy QA benchmark, AlpaCare-13B beat Mistral-7B and BioMistral-7B-DARE in accuracy and safety, but all models dropped on complex reasoning.